On Fri, 30 May 2008, Peter Zijlstra wrote: > > > Also, it explicitly ties the preempt-off section to the data used in > > > case of !rt, which in turn allows for the direct conversion to the > > > locked version. > > > > Ahh. Okay. This would make the lockless preemptless fastpath impossible > > because it would have to use some sort of locking to avoid access to the > > same percpu data from multiple processor? > > TBH its been a while since I attempted slub-rt, but yes that got hairy. > I think it can be done using cmpxchg and speculative page refs, but I > can't quite recall. Uhhh... Well I think you really need two different percpu sections. One that works like the upstream percpu section and another where it works with a spinlock. Basically its like a struct protected by an extra lock. The one with a spinlock could not support the atomic percpu ops. -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
